|
{ |
|
"name": "root", |
|
"gauges": { |
|
"Pyramids.Policy.Entropy.mean": { |
|
"value": 0.49476349353790283, |
|
"min": 0.4852714538574219, |
|
"max": 1.4339741468429565, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.Entropy.sum": { |
|
"value": 14977.48046875, |
|
"min": 14538.595703125, |
|
"max": 43501.0390625, |
|
"count": 26 |
|
}, |
|
"Pyramids.Step.mean": { |
|
"value": 779914.0, |
|
"min": 29952.0, |
|
"max": 779914.0, |
|
"count": 26 |
|
}, |
|
"Pyramids.Step.sum": { |
|
"value": 779914.0, |
|
"min": 29952.0, |
|
"max": 779914.0, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.mean": { |
|
"value": 0.3168967366218567, |
|
"min": -0.12174516171216965, |
|
"max": 0.3173356056213379, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.ExtrinsicValueEstimate.sum": { |
|
"value": 83.66073608398438, |
|
"min": -28.85360336303711, |
|
"max": 83.66073608398438, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.mean": { |
|
"value": 0.0046995291486382484, |
|
"min": 0.0033017457462847233, |
|
"max": 0.4047175347805023, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.RndValueEstimate.sum": { |
|
"value": 1.240675687789917, |
|
"min": 0.8155311942100525, |
|
"max": 95.91805267333984, |
|
"count": 26 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.mean": { |
|
"value": 0.06966448413108342, |
|
"min": 0.06553156230515046, |
|
"max": 0.07370801784734896, |
|
"count": 26 |
|
}, |
|
"Pyramids.Losses.PolicyLoss.sum": { |
|
"value": 0.9753027778351679, |
|
"min": 0.4833440314229021, |
|
"max": 1.0600366913268398, |
|
"count": 26 |
|
}, |
|
"Pyramids.Losses.ValueLoss.mean": { |
|
"value": 0.018042720152672182, |
|
"min": 3.756502231914526e-05, |
|
"max": 0.018042720152672182, |
|
"count": 26 |
|
}, |
|
"Pyramids.Losses.ValueLoss.sum": { |
|
"value": 0.25259808213741053, |
|
"min": 0.0004883452901488884, |
|
"max": 0.25259808213741053, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.LearningRate.mean": { |
|
"value": 1.2960176037116072e-05, |
|
"min": 1.2960176037116072e-05, |
|
"max": 0.00029393828773485714, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.LearningRate.sum": { |
|
"value": 0.000181442464519625, |
|
"min": 0.000181442464519625, |
|
"max": 0.0033915905444698753, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.Epsilon.mean": { |
|
"value": 0.1043200267857143, |
|
"min": 0.1043200267857143, |
|
"max": 0.19797942857142856, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.Epsilon.sum": { |
|
"value": 1.4604803750000002, |
|
"min": 1.3613920000000002, |
|
"max": 2.51128725, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.Beta.mean": { |
|
"value": 0.0004415706758928571, |
|
"min": 0.0004415706758928571, |
|
"max": 0.009798144914285713, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.Beta.sum": { |
|
"value": 0.0061819894625, |
|
"min": 0.0061819894625, |
|
"max": 0.11306995948750001, |
|
"count": 26 |
|
}, |
|
"Pyramids.Losses.RNDLoss.mean": { |
|
"value": 0.013691753149032593, |
|
"min": 0.013691753149032593, |
|
"max": 0.46661216020584106, |
|
"count": 26 |
|
}, |
|
"Pyramids.Losses.RNDLoss.sum": { |
|
"value": 0.1916845440864563, |
|
"min": 0.1916845440864563, |
|
"max": 3.2662851810455322, |
|
"count": 26 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.mean": { |
|
"value": 477.4788732394366, |
|
"min": 477.4788732394366, |
|
"max": 999.0, |
|
"count": 26 |
|
}, |
|
"Pyramids.Environment.EpisodeLength.sum": { |
|
"value": 33901.0, |
|
"min": 15984.0, |
|
"max": 33901.0, |
|
"count": 26 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.mean": { |
|
"value": 1.2971041938158827, |
|
"min": -1.0000000521540642, |
|
"max": 1.2971041938158827, |
|
"count": 26 |
|
}, |
|
"Pyramids.Environment.CumulativeReward.sum": { |
|
"value": 92.09439776092768, |
|
"min": -32.000001668930054, |
|
"max": 92.09439776092768, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.mean": { |
|
"value": 1.2971041938158827, |
|
"min": -1.0000000521540642, |
|
"max": 1.2971041938158827, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.ExtrinsicReward.sum": { |
|
"value": 92.09439776092768, |
|
"min": -32.000001668930054, |
|
"max": 92.09439776092768, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.RndReward.mean": { |
|
"value": 0.06791334474991358, |
|
"min": 0.06791334474991358, |
|
"max": 9.313939461484551, |
|
"count": 26 |
|
}, |
|
"Pyramids.Policy.RndReward.sum": { |
|
"value": 4.821847477243864, |
|
"min": 3.9129698085598648, |
|
"max": 149.02303138375282, |
|
"count": 26 |
|
}, |
|
"Pyramids.IsTraining.mean": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 26 |
|
}, |
|
"Pyramids.IsTraining.sum": { |
|
"value": 1.0, |
|
"min": 1.0, |
|
"max": 1.0, |
|
"count": 26 |
|
} |
|
}, |
|
"metadata": { |
|
"timer_format_version": "0.1.0", |
|
"start_time_seconds": "1673412704", |
|
"python_version": "3.8.16 (default, Dec 7 2022, 01:12:13) \n[GCC 7.5.0]", |
|
"command_line_arguments": "/usr/local/bin/mlagents-learn ./config/ppo/PyramidsRND.yaml --env=./training-envs-executables/linux/Pyramids/Pyramids --run-id=Pyramids Training --no-graphics --force", |
|
"mlagents_version": "0.29.0.dev0", |
|
"mlagents_envs_version": "0.29.0.dev0", |
|
"communication_protocol_version": "1.5.0", |
|
"pytorch_version": "1.8.1+cu102", |
|
"numpy_version": "1.21.6", |
|
"end_time_seconds": "1673414420" |
|
}, |
|
"total": 1715.4272575219998, |
|
"count": 1, |
|
"self": 0.44289045599998644, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.11044421999986298, |
|
"count": 1, |
|
"self": 0.11044421999986298 |
|
}, |
|
"TrainerController.start_learning": { |
|
"total": 1714.873922846, |
|
"count": 1, |
|
"self": 1.1755026050377637, |
|
"children": { |
|
"TrainerController._reset_env": { |
|
"total": 6.708610992000104, |
|
"count": 1, |
|
"self": 6.708610992000104 |
|
}, |
|
"TrainerController.advance": { |
|
"total": 1706.6131214679617, |
|
"count": 50714, |
|
"self": 1.1257404760258396, |
|
"children": { |
|
"env_step": { |
|
"total": 1106.7132887349285, |
|
"count": 50714, |
|
"self": 1013.182600981931, |
|
"children": { |
|
"SubprocessEnvManager._take_step": { |
|
"total": 92.84420582597568, |
|
"count": 50714, |
|
"self": 3.719329618028951, |
|
"children": { |
|
"TorchPolicy.evaluate": { |
|
"total": 89.12487620794673, |
|
"count": 50036, |
|
"self": 28.34038994091543, |
|
"children": { |
|
"TorchPolicy.sample_actions": { |
|
"total": 60.7844862670313, |
|
"count": 50036, |
|
"self": 60.7844862670313 |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"workers": { |
|
"total": 0.6864819270217595, |
|
"count": 50714, |
|
"self": 0.0, |
|
"children": { |
|
"worker_root": { |
|
"total": 1710.8475445879963, |
|
"count": 50714, |
|
"is_parallel": true, |
|
"self": 781.9695121539357, |
|
"children": { |
|
"run_training.setup": { |
|
"total": 0.0, |
|
"count": 0, |
|
"is_parallel": true, |
|
"self": 0.0, |
|
"children": { |
|
"steps_from_proto": { |
|
"total": 0.0019001539999408124, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0007326949994421739, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0011674590004986385, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0011674590004986385 |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 0.045284408000043186, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005797870003334538, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 0.0005046559999755118, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0005046559999755118 |
|
}, |
|
"communicator.exchange": { |
|
"total": 0.0424804609997409, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.0424804609997409 |
|
}, |
|
"steps_from_proto": { |
|
"total": 0.0017195039999933215, |
|
"count": 1, |
|
"is_parallel": true, |
|
"self": 0.00042736199975479394, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 0.0012921420002385275, |
|
"count": 8, |
|
"is_parallel": true, |
|
"self": 0.0012921420002385275 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"UnityEnvironment.step": { |
|
"total": 928.8780324340605, |
|
"count": 50713, |
|
"is_parallel": true, |
|
"self": 23.856492721886752, |
|
"children": { |
|
"UnityEnvironment._generate_step_input": { |
|
"total": 19.09114741005851, |
|
"count": 50713, |
|
"is_parallel": true, |
|
"self": 19.09114741005851 |
|
}, |
|
"communicator.exchange": { |
|
"total": 799.9183385970555, |
|
"count": 50713, |
|
"is_parallel": true, |
|
"self": 799.9183385970555 |
|
}, |
|
"steps_from_proto": { |
|
"total": 86.01205370505977, |
|
"count": 50713, |
|
"is_parallel": true, |
|
"self": 19.120138897982542, |
|
"children": { |
|
"_process_rank_one_or_two_observation": { |
|
"total": 66.89191480707723, |
|
"count": 405704, |
|
"is_parallel": true, |
|
"self": 66.89191480707723 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_advance": { |
|
"total": 598.7740922570074, |
|
"count": 50714, |
|
"self": 2.0756053139748474, |
|
"children": { |
|
"process_trajectory": { |
|
"total": 123.20095220503754, |
|
"count": 50714, |
|
"self": 122.80800626103746, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.39294594400007554, |
|
"count": 1, |
|
"self": 0.39294594400007554 |
|
} |
|
} |
|
}, |
|
"_update_policy": { |
|
"total": 473.497534737995, |
|
"count": 355, |
|
"self": 168.17626016899158, |
|
"children": { |
|
"TorchPPOOptimizer.update": { |
|
"total": 305.32127456900344, |
|
"count": 18261, |
|
"self": 305.32127456900344 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
}, |
|
"trainer_threads": { |
|
"total": 1.184000211651437e-06, |
|
"count": 1, |
|
"self": 1.184000211651437e-06 |
|
}, |
|
"TrainerController._save_models": { |
|
"total": 0.3766865970001163, |
|
"count": 1, |
|
"self": 0.00976375500067661, |
|
"children": { |
|
"RLTrainer._checkpoint": { |
|
"total": 0.3669228419994397, |
|
"count": 1, |
|
"self": 0.3669228419994397 |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |
|
} |